Open AccessComparison of GANs for Covid-19 X-ray classification
Author(s) -
Luiz Felipe Cavalcanti,
Lilian Berton
Publication year - 2021
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5753/eniac.2021.18238
Subject(s) - computer science , artificial intelligence , task (project management) , process (computing) , adversarial system , machine learning , contextual image classification , artificial neural network , covid-19 , pattern recognition (psychology) , generative grammar , image (mathematics) , data mining , medicine , management , disease , pathology , infectious disease (medical specialty) , economics , operating system
Image classification has been applied to several real problems. However, getting labeled data is a costly task, since it demands time, resources and experts. Furthermore, some domains like disease detection suffer from unbalanced classes. These scenarios are challenging and degrade the performance of machine learning algorithms. In these cases, we can use Data Augmentation (DA) approaches to increase the number of labeled examples in a dataset. The objective of this work is to analyze the use of Generative Adversarial Networks (GANs) as DA, which are capable of synthesizing artificial data from the original data, under an adversarial process of two neural networks. The GANs are applied in the classification of unbalanced Covid-19 radiological images. Increasing the number of images led to better accuracy for all the GANs tested, especially in the multi-label dataset, mitigating the bias for unbalanced classes.